Comparison of machine learning algorithms to predict intentional and unintentional poisoning risk factors

Introduction

A major share of poisoning cases are perpetrated intentionally, but this varies depending on different geographical regions, age spectrums, and gender distribution. The present study was conducted to determine the most important factors affecting intentional and unintentional poisonings using machine learning algorithms.

Materials and methods

The current cross-sectional study was conducted on 658 people hospitalized due to poisoning. The enrollment and follow-up of patients were carried out during 2020-2021. The data obtained from patients' files and during follow-up were recorded by a physician and entered into SPSS software by the registration expert. Different machine learning algorithms were used to analyze the data. Fit models of the training data were assessed by determining accuracy, sensitivity, specificity, F-measure, and the area under the rock curve (AUC). Finally, after analyzing the models, the data of the Gradient boosted trees (GBT) model were finalized.

Results

The GBT model rendered the highest accuracy (91.5 ± 3.4) among other models tested. Also, the GBT model had significantly higher sensitivity (94.7 ± 1.7) and specificity (93.2 ± 4.1) compared to other models (P < 0.001). The most prominent predictors based on the GBT model were the route of poison entry (weight = 0.583), place of residence (weight = 0.137), history of psychiatric diseases (weight = 0.087), and age (weight = 0.085).

Conclusion

The present study suggests the GBT model as a reliable predictor model for identifying the factors affecting intentional and unintentional poisoning. According to our results, the determinants of intentional poisoning included the route of poison entry into the body, place of residence, and the heart rate. The most important predictors of unintentional poisoning were age, exposure to benzodiazepine, creatinine levels, and occupation.

Development of a new clinical tool to evaluate the balance abilities of children with bilateral vestibular loss: The Geneva Balance Test

Introduction

Vestibular deficits are considered rare in children, but the lack of systematic screening leads to underdiagnosis. It has been demonstrated that chronic vestibular dysfunction impacts the normal psychomotor development of children. Early identification is needed to allow for clinical management, ensuring better global development. For this purpose, our research group has developed the Geneva Balance Test (GBT), aiming to objectively quantify the balance capacity of children over a broad age range, to screen for bilateral vestibulopathy (BV), and to quantify the improvement of balance abilities in children.

Methods

To determine the capacity of the GBT to quantify the balance capacity of children with BV, we conducted an observational prospective study with three populations: 11 children with BV, and two age-matched control groups composed of (1) 15 healthy subjects without the vestibular or auditory disorder (HS) and (2) 11 pediatric cochlear implant recipients (CIs) without vestibular disorders. Results of the three populations have been compared in three different age sub- groups (3-5, 6-9, and ≥10 years), and with results of a short, modified version of the Bruininks-Oseretsky test of Motor proficiency Ed. 2 (mBOT-2).

Results

Statistical analyses demonstrated significant differences in the scores of the GBT between children aged 3-5, 6-9, and ≥10 years with BV and in both control populations (HS and CI). BV scores reflected poorer balance capacities at all ages. Children in the youngest CI sub-group (3-5 years) showed intermediate GBT scores but reached HS scores at 6-9 years, reflecting an improvement in their balance capacities. All the results of the GBT were significantly correlated with mBOT-2 results, although only a few BV completed the entire mBOT-2.

Discussion

In this study, the GBT allowed quantifying balance deficits in children with BV. The BOT-2 test is not validated for children <4.5 years of age, and the GBT seems to be better tolerated in all populations than the mBOT-2. Furthermore, mBOT-2 results saturated, reaching maximum values by 6-9 years whereas the GBT did not, suggesting that the GBT could be a useful tool for monitoring the development of balance capacities with age and could be used in the follow-up of children with severe vestibular disorders.

Early detection of Alzheimer's disease using single nucleotide polymorphisms analysis based on gradient boosting tree

Alzheimer's disease (AD) is a degenerative disorder that attacks nerve cells in the brain. AD leads to memory loss and cognitive & intellectual impairments that can influence social activities and decision-making. The most common type of human genetic variation is single nucleotide polymorphisms (SNPs). SNPs are beneficial markers of complex gene-disease. Many common and serious diseases, such as AD, have associated SNPs. Detection of SNP biomarkers linked with AD could help in the early prediction and diagnosis of this disease. The main objective of this paper is to predict and diagnose AD based on SNPs biomarkers with high classification accuracy in the early stages. One of the most concerning problems is the high number of features. Thus, the paper proposes a comprehensive framework for early AD detection and detecting the most significant genes based on SNPs analysis. Usage of machine learning (ML) techniques to identify new biomarkers of AD is also suggested. In the proposed system, two feature selection techniques are separately checked: the information gain filter and Boruta wrapper. The two feature selection techniques were used to select the most significant genes related to AD in this system. Filter methods measure the relevance of features by their correlation with dependent variables, while wrapper methods measure the usefulness of a subset of features by training a model on it. Gradient boosting tree (GBT) has been applied on all AD genetic data of neuroimaging initiative phase 1 (ADNI-1) and Whole-Genome Sequencing (WGS) datasets by using two feature selection techniques. In the whole-genome approach ADNI-1, results revealed that the GBT learning algorithm scored an overall accuracy of 99.06% in the case of using Boruta feature selection. Using information gain feature selection, the proposed system achieved an average accuracy of 94.87%. The results show that the proposed system is preferable for the early detection of AD. Also, the results revealed that the Boruta wrapper feature selection is superior to the information gain filter technique.

Compressive Strength Estimation of Fly Ash/Slag Based Green Concrete by Deploying Artificial Intelligence Models

Cement production is one of the major sources of decomposition of carbonates leading to the emission of carbon dioxide. Researchers have proven that incorporating industrial wastes is of paramount significance for producing green concrete due to the benefits of reducing cement production. The compressive strength of concrete is an imperative parameter to consider when designing concrete structures. Considering high prediction capabilities, artificial intelligence models are widely used to estimate the compressive strength of concrete mixtures. A variety of artificial intelligence models have been developed in the literature; however, evaluation of the modeling procedure and accuracy of the existing models suggests developing such models that manifest the detailed evaluation of setting parameters on the performance of models and enhance the accuracy compared to the existing models. In this study, the computational capabilities of the adaptive neurofuzzy inference system (ANFIS), gene expression programming (GEP), and gradient boosting tree (GBT) were employed to investigate the optimum ratio of ground-granulated blast furnace slag (GGBFS) and fly ash (FA) to the binder content. The training process of GEP modeling revealed 200 chromosomes, 5 genes, and 12 head sizes as the best hyperparameters. Similarly, ANFIS hybrid subclustering modeling with aspect ratios of 0.5, 0.1, 7, and 150; learning rate; maximal depth; and number of trees yielded the best performance in the GBT model. The accuracy of the developed models suggests that the GBT model is superior to the GEP, ANFIS, and other models that exist in the literature. The trained models were validated using 40% of the experimental data along with parametric and sensitivity analysis as second level validation. The GBT model yielded correlation coefficient (R), mean absolute error (MAE), and root mean square error (RMSE), equaling 0.95, 3.07 MPa, and 4.80 MPa for training, whereas, for validation, these values were recorded as 0.95, 3.16 MPa, and 4.85 MPa, respectively. The sensitivity analysis revealed that the aging of the concrete was the most influential parameter, followed by the addition of GGBFS. The effect of the contributing parameters was observed, as corroborated in the literature.

Artificial Flora Algorithm-Based Feature Selection with Gradient Boosted Tree Model for Diabetes Classification

PURPOSE

Classification of medical data is essential to determine diabetic treatment options; therefore, the objective of the study was to develop a model to classify the three diabetes type diagnoses according to multiple patient attributes.

METHODS

Three different datasets are used to develop a novel medical data classification model. The proposed model involved preprocessing, artificial flora algorithm (AFA)-based feature selection, and gradient boosted tree (GBT)-based classification. Then, the processing occurred in two steps, namely, format conversion and data transformation. AFA was applied for selecting features, such as demographics, vital signs, laboratory tests, medications, from the patients' electronic health records. Lastly, the GBT-based classification model was applied for classifying the patients' cases to type I, type II, or gestational diabetes mellitus.

RESULTS

The effectiveness of the proposed AFA-GBT model was validated using three diabetes datasets to classify patient cases into one of the three different types of diabetes. The proposed model showed a maximum average precision of 91.64%, a recall of 97.46%, an accuracy of 99.93%, an F-score of 94.19%, and a kappa of 96.61%.

CONCLUSION

The AFA-GBT model could classify patient diagnoses into the three diabetes types efficiently.

The World Health Organization Global Benchmarking Tool an Instrument to Strengthen Medical Products Regulation and Promote Universal Health Coverage

National regulatory authorities (NRAs) are the gatekeepers of the supply chain of medical products, and they have a mandate to ensure the quality, safety and efficacy of medicines, vaccines, blood, and blood products, medical devices, including diagnostics and traditional, or herbal medicines. However, the majority of the world's regulators are still struggling to reach a level of maturity, whereby they have a stable, well-functioning and integrated regulatory system. The World Health Organization (WHO) has developed a Global Benchmarking Tool (GBT) as part of its five-step capacity building program to assist NRAs, using the tool, they can benchmark their own strengths and areas of weakness, and then engage in a formal benchmarking process together with WHO and international experts in order to formulate an effective and workable institutional development plan. The GBT is comprehensive across the entire product life cycle and allows benchmarking to be customized to the needs of the NRA. It has evolved from decades of experience using a variety of benchmarking tools, within WHO and other stakeholder organizations. By the end of December 2019, 26 countries had undergone formal benchmarking, and a further 54 countries had used the GBT to conduct self-benchmarking exercises assisted by WHO.

Effects of antiepileptic drugs on mitochondrial functions, morphology, kinetics, biogenesis, and survival

OBJECTIVES

Antiepileptic drugs (AEDs) exhibit adverse and beneficial effects on mitochondria, which have a strong impact on the treatment of patients with a mitochondrial disorder (MID) with epilepsy (mitochondrial epilepsy). This review aims at summarizing and discussing recent findings concerning the effect of AEDs on mitochondrial functions and the clinical consequences with regard to therapy of mitochondrial epilepsy and of MIDs in general.

METHODS

Literature review.

RESULTS

AEDs may interfere with the respiratory chain, with non-respiratory chain enzymes, carrier proteins, or mitochondrial biogenesis, with carrier proteins, membrane-bound channels or receptors and the membrane potential, with anti-oxidative defense mechanisms, with morphology, dynamics and survival of mitochondria, and with the mtDNA. There are AEDs of which adverse effects outweigh beneficial effects, such as valproic acid, carbamazepine, phenytoin, or phenobarbital and there are AEDs in which beneficial effects dominate over mitochondrial toxic effects, such as lamotrigine, levetiracetam, gabapentin, or zonisamide. However, from most AEDs only little is known about their interference with mitochondria.

CONCLUSIONS

Mitochondrial epilepsy might be initially treated with AEDs with low mitochondrial toxic potential. Only in case mitochondrial epilepsy is refractory to these AEDs, AEDs with higher mitochondrial toxic potential might be tried. In patients carrying POLG1 mutations AEDs with high mitochondrial toxic potential are contraindicated.